Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    differ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Transaction
    -0.07
     тан
    -0.07
    ynamic
    -0.07
    _CAST
    -0.07
    useRal
    -0.07
     sorumlu
    -0.07
     Sanct
    -0.07
    ІІ
    -0.07
     انت
    -0.06
     returnValue
    -0.06
    POSITIVE LOGITS
     differed
    0.07
     Erin
    0.07
     differ
    0.07
    iffer
    0.06
    
    0.06
     Dich
    0.06
    》，
    0.06
    Aff
    0.06
     chị
    0.06
    994
    0.06
    Act Density 0.006%

    No Known Activations